Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Nam, Jinhwan"'
Diffusion models have become a cornerstone in image editing, offering flexibility with language prompts and source images. However, a key challenge is attribute leakage, where unintended modifications occur in non-target regions or within target regi
Externí odkaz:
http://arxiv.org/abs/2412.04715
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model. The target dataset is often assumed to be fully identifiable in a standard unlearning scenario. Such a flawless
Externí odkaz:
http://arxiv.org/abs/2205.15567